Immutable model versions
Registered artifacts have SHA-256 identities, verified before execution, with local or S3-compatible storage behind one contract.
ML deployment infrastructureModelForge.
Version a model. Release progressively. Preserve the stable service.
A model registry and deployment control plane with immutable artifacts, weighted canaries, promotion, rollback, and runtime boundaries.
ModelForge / SYSTEM MAP
Register · canary · promote or recover
164 tests passedRECORDED CHECKPOINT
THE IDEA
What ModelForge does.
ModelForge is a model registry, deployment control plane and inference platform. Browser, CLI and API clients use the same operations to register immutable model versions, select a runtime, send a weighted share of requests to a canary and promote, abort or roll back a release.
Progressive release controls
Weighted canaries receive controlled traffic. Promotion, abort and rollback preserve validated lifecycle transitions and environment targets.
Framework-independent execution
Built-in, PyTorch and ONNX runtimes share an interface. An external HTTP contract supports the reference Go runtime and future plugins.
Runtime failure containment
Health inspection, bounded retries, circuit breakers, metrics and stable fallback govern execution at the runtime boundary.
BUILT WITH
The technology.
FROM INPUT TO OUTCOME
How it works.
Shipping a model is a release-management problem as well as an inference problem. An artifact must retain a verifiable identity, a candidate needs bounded exposure, and a failed new version must preserve the stable target.
01 / 04
Register
Create a workspace-scoped model and immutable version, then upload and verify its artifact.
ModelForge / SYSTEM MAP
Register · canary · promote or recover
ENGINEERING DECISIONS
Why it’s built this way.
Control plane and execution are separate
The Python/FastAPI control plane owns identity, state, traffic and tenancy. Runtimes own framework-specific loading and prediction, so a new framework does not require serving-path branches.
Atomic release invariants
A canary does not become stable until promotion succeeds. Promotion and rollback update release state and environment targets transactionally.
Workspace boundaries throughout
Models, artifacts, deployments, canaries and keys are workspace-scoped. Browser sessions use OIDC/PKCE; automation uses hashed workspace API keys.
RECORDED CHECKPOINTS
What the evidence shows.
The recorded CI checkpoint passed 164 tests with 3 skips. The deployment validation scenario serves a baseline, observes weighted canary traffic, promotes v2, restores v1, detects an intentionally regressed v3 and aborts it while v1 remains authoritative.
164Tests passed in recorded CI
3Recorded test skips
SHA-256Immutable artifact identity
RECORDED VALIDATION SCENARIO
01Serve v102Canary v203Promote v204Restore v105Abort regressed v3
v1 remains authoritative after the deliberately failed canary.
SCOPE & LIMITS
Read the engineering brief PDFModelForge is not publicly hosted. The console preview uses example data and is illustrative. AWS/Terraform configuration is a deployment reference, not proof of live AWS operation. Model caches and runtime client state are currently process-local.
OPEN THE WORK
Code, documents & proof.
A concise engineering brief and direct links to the implementation and supporting evidence.
ENGINEERING BRIEFModelForgeMichael Baffour Awuah · 2026
Inside the engineering
A two-page project brief covering the purpose, workflow, design decisions, recorded checks, and limits.